PCAOT: A Manhattan Point Cloud Registration Method Towards Large Rotation and Small Overlap

Point cloud registration is a popular research topic and has been widely used in many tasks, such as robot mapping and localization. It is a challenging problem when the overlap is small, or the rotation is large. The problem has not been well solved by existing methods such as the iterative closest point (ICP) and its variants. In this paper, a novel method named principal coordinate alignment with overlap tuning (PCAOT) is proposed based on the Manhattan world assumption. It solves two key problems together, the transformation estimation and the overlap estimation. The overlap is represented by a 3D cuboid and the transformation is computed only within the overlap region. Instead of finding point correspondence as in traditional methods, we estimate the rotation by principal coordinates alignment, which is faster and less sensitive than ICP and its variants to small overlaps and large rotations. Evaluations demonstrate that our method achieves much better results than the ICP and its variants when the overlap ratio is smaller than 50%, or the rotation angle is larger than 60°. Especially, it is effective when the overlap ratio is less than 30%, or the rotation angle is larger than 90°.

[1]  Ian D. Reid,et al.  A Dynamic Programming Approach to Reconstructing Building Interiors , 2010, ECCV.

[2]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Andrew W. Fitzgibbon,et al.  Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Jian Zhao,et al.  Fast and Accurate Registration of Structured Point Clouds with Small Overlaps , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[5]  Eric Mjolsness,et al.  New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence , 1998, NIPS.

[6]  Pavel Krsek,et al.  Robust Euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm , 2005, Image Vis. Comput..

[7]  Melba M. Crawford,et al.  Point-to-plane registration of terrestrial laser scans , 2012 .

[8]  Yong Zhuo,et al.  Automatic registration of partial overlap three-dimensional surfaces , 2010, 2010 International Conference on Mechanic Automation and Control Engineering.

[9]  Federico Tombari,et al.  Unique Signatures of Histograms for Local Surface Description , 2010, ECCV.

[10]  Gérard G. Medioni,et al.  Object modeling by registration of multiple range images , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[11]  Andreas Birk,et al.  Fast Registration Based on Noisy Planes With Unknown Correspondences for 3-D Mapping , 2010, IEEE Transactions on Robotics.

[12]  Jiaolong Yang,et al.  Go-ICP: Solving 3D Registration Efficiently and Globally Optimally , 2013, 2013 IEEE International Conference on Computer Vision.

[13]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[14]  Duc Thanh Nguyen,et al.  SceneNN: A Scene Meshes Dataset with aNNotations , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[15]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[16]  Giorgio Grisetti,et al.  NICP: Dense normal based point cloud registration , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[17]  Adrien Bartoli,et al.  3D Shape Registration , 2012, 3D Imaging, Analysis and Applications.

[18]  Simona Nobili,et al.  Overlap-based ICP tuning for robust localization of a humanoid robot , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.